TY - JOUR
TI - Physics-informed machine learning
AU - Karniadakis, George Em
AU - Kevrekidis, Ioannis G.
AU - Lu, Lu
AU - Perdikaris, Paris
AU - Wang, Sifan
AU - Yang, Liu
T2 - Nature Reviews Physics
AB - Despite great progress in simulating multiphysics problems using the numerical discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate noisy data into existing algorithms, mesh generation remains complex, and high-dimensional problems governed by parameterized PDEs cannot be tackled. Moreover, solving inverse problems with hidden physics is often prohibitively expensive and requires different formulations and elaborate computer codes. Machine learning has emerged as a promising alternative, but training deep neural networks requires big data, not always available for scientific problems. Instead, such networks can be trained from additional information obtained by enforcing the physical laws (for example, at random points in the continuous space-time domain). Such physics-informed learning integrates (noisy) data and mathematical models, and implements them through neural networks or other kernel-based regression networks. Moreover, it may be possible to design specialized network architectures that automatically satisfy some of the physical invariants for better accuracy, faster training and improved generalization. Here, we review some of the prevailing trends in embedding physics into machine learning, present some of the current capabilities and limitations and discuss diverse applications of physics-informed learning both for forward and inverse problems, including discovering hidden physics and tackling high-dimensional problems.
DA - 2021/06//
PY - 2021
DO - 10.1038/s42254-021-00314-5
DP - www.nature.com
VL - 3
IS - 6
SP - 422
EP - 440
J2 - Nat Rev Phys
LA - en
SN - 2522-5820
UR - https://www.nature.com/articles/s42254-021-00314-5
Y2 - 2022/01/19/01:31:07
KW - Applied mathematics
KW - Computational science
ER -